© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87810
    Prev
    Next
    INDEX
    Explanations

    references to volumes and parts of works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ens
    -0.06
    -0.06
    line
    -0.06
    rol
    -0.06
     line
    -0.06
     sor
    -0.05
     conv
    -0.05
    als
    -0.05
     ho
    -0.05
     haz
    -0.05
    POSITIVE LOGITS
     fitte
    0.09
    klad
    0.09
    imeo
    0.09
    .EVT
    0.09
    olucion
    0.09
    agini
    0.08
     geile
    0.08
    째
    0.08
    engo
    0.08
    imest
    0.08
    Activations Density 0.007%

    No Known Activations